© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38508
    Prev
    Next
    INDEX
    Explanations

    arguments versus opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    享
    -0.09
    æľķ
    -0.09
    ä»ħ次
    -0.09
    å¸Ŀçİĭ
    -0.08
    æľīæĦıæĢĿçļĦ
    -0.08
    误ä¼ļ
    -0.08
    èµŀèµı
    -0.08
    éű
    -0.08
    åĨ¶
    -0.08
    å¢ĥçķĮ
    -0.08
    POSITIVE LOGITS
    认为
    0.18
    èªįçĤº
    0.14
    éĺµèIJ¥
    0.13
    æĭ¥æĬ¤
    0.13
     argue
    0.12
    æľī人说
    0.11
    æľīçļĦ人
    0.11
    åı¦ä¸Ģè¾¹
    0.11
     arguments
    0.11
    æľīçļĦ
    0.11
    Activations Density 0.088%

    No Known Activations